Journal of the Institute of Electronics Engineers of Korea CI (전자공학회논문지CI)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Texture Descriptor for Texture-Based Image Retrieval and Its Application in Computer-Aided Diagnosis System

질감 기반 이미지 검색을 위한 질감 서술자 및 컴퓨터 조력 진단 시스템의 적용

  • Received : 2010.06.01
  • Accepted : 2010.07.07
  • Published : 2010.07.25
Download PDF
⟨ Previous Next ⟩

Abstract

Texture information plays an important role in object recognition and classification. To perform an accurate classification, the texture feature used in the classification must be highly discriminative. This paper presents a novel texture descriptor for texture-based image retrieval and its application in Computer-Aided Diagnosis (CAD) system for Emphysema classification. The texture descriptor is based on the combination of local surrounding neighborhood difference and centralized neighborhood difference and is named as Combined Neighborhood Difference (CND). The local differences of surrounding neighborhood difference and centralized neighborhood difference between pixels are compared and converted into binary codewords. Then binomial factor is assigned to the codewords in order to convert them into high discriminative unique values. The distribution of these unique values is computed and used as the texture feature vectors. The texture classification accuracies using Outex and Brodatz dataset show that CND achieves an average of 92.5%, whereas LBP, LND and Gabor filter achieve 89.3%, 90.7% and 83.6%, respectively. The implementations of CND in the computer-aided diagnosis of Emphysema is also presented in this paper.

질감 정보는 객체 인식과 분류에서 중요한 역할을 하고 있다. 정확한 질환 판별을 위해 분류에서 사용되는 질감 특징은 식별성이 높아야 한다. 본 논문에서는 질감-기반 영상 검색 및 폐기종 진단을 위해 컴퓨터 조력진단(Computer-Aided Diagnosis) 시스템을 위한 새로운 질감 기술자를 제안한다. 제안한 질감 기술자는 이웃화소간의 차이값과 중심화소와 이웃화소간의 차이 값의 결합에 기반을 두고 있어 결합된 주변화소 차이(Combined Neighborhood Difference; CND)라고 한다. 화소들간의 CND는 비교후 이진 코드워드로 변환된다. 그다음에, 식별성이 높은 값을 생성하기 위하여 이진 계수가 코드워드에 할당된다. 이와 같은 값들의 분포가 계산되어 질감 특징 벡터를 구성한다. Outex와 Brodatz 데이터집합을 이용한 질감 특징 분류에 관련하여 CND는 92.5%의 정확성을 보이는 데 비해, LBP, LND와 Gabor 픽터는 89.3%, 90.7%와 83.6%의 정확성을 각각 보여준다. 본 논문에서는 CND를 이용한 폐기종의 진단 기능을 CAD 시스템에서 구현하였다.

Keywords

Acknowledgement

Supported by : 한국연구재단

References

  1. Julesz B, "Textons, The fundamental elements in preattentive vision and perception of textures", Bell Syst Tech J 62(6), pp. 1619-1645, 1997.
  2. Haralick R, "Statistical and structural approaches to texture", Proc. IEEE, vol. 67, no. 5, pp. 786-804., 1979. https://doi.org/10.1109/PROC.1979.11328
  3. Manjunathi, B.S., Ma, W.Y.: Texture features for browsing and retrieval of image data. IEEE Trans. Pattern Anal. Machine Intell. 18(8), pp. 837-842, 1996. https://doi.org/10.1109/34.531803
  4. Timo Ojala, Matti Pietikainen and David Harwood, "A Comparative Study of Texture Measures With Classification Based on Feature Distributions", Pat. Recog., pp. 51-59, 1996.
  5. Feng Zhou, Ju-ju Feng and Qing-Yun Shi, "Texture Feature Based on Local Fourier Transform", Proc. ICIP, pp.610-613, 2001.
  6. Khairul Muzzammil Saipullah, Shao-Hu Peng, Hyun-Soo Kim, Deok-Hwan Kim, "Texture Classification By Implementing Blur, Scale and Grey Shift Insensitive Texture Descriptor Based on Local Fourier Transform", Proc. IWAIT, pp. 74, 2010.
  7. Khairul Muzzammil, Shao-hu Peng, Min-Wook Park and Deok-Hwan Kim, "Texture Classification Using Local Neighbor Differences", Proc. KIPS Spring Conf., 2010.
  8. Timo Ojala, Matti Pietikainen and Topi Maenpa, "Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Pattern", IEEE Trans. Pat. Analysis and Machine Intelligence, Vol. 24, No. 7, pp. 971-987, 2002. https://doi.org/10.1109/TPAMI.2002.1017623
  9. 이덕운, 남우현, 나종범, "진단 및 치료를 위한 3차원 의료 영상의 응용", 대한전자공학회 전자공학회지, 제35권, 제4호, pp. 67-75, 2008년 4월.
  10. A. M. R. Schilham, B. V. Ginneken, and M. Loog, "A Computer-Aided Diagnosis System for Detection of Lung Nodules in Chest Radiographs with an Evaluation on a Public Database", Medical Image Analysis, vol. 10, pp. 247-258, 2006. https://doi.org/10.1016/j.media.2005.09.003
  11. T. K. Liang, T. Tanaka, H. Nakamura and A. Ishizaka, "A Neural Network based Computer -Aided Diagnosis of Emphysema using CT Lung Images", SICE Annual Conference 2007, pp. 703-709, 2007.
  12. Shao-Hu Peng, Hyun-Soo Kim and Deok-Hwan Kim, "Speeded Up Feature Extraction for CT image Based on Integral Image Technique", IFMIA, pp. 319-324, 2009.
  13. 뮤잠멜, 팽소호, 김현수, 김덕환,"Seeded Region Growing 기법을 이요한 폐영역검출",전자공학회 추계학술대회, pp. 371-372, 2009.
  14. Jie Chen, Shiguang Shan, Chu He, Guoying Zhao, Matti Pietikainen, Xilin Chen, Wen Gao, "WLD: A Ro-bust Local Image Descriptor," IEEE Trans. Pat. Analysis and Machine Intell. vol. 99, 2009.
  15. http://www.ux.uis.no/～tranden/brodatz.html.
  16. Khairul Muzzammil, Shao-hu Peng, Hyun-Soo Kim and Deok-Hwan Kim, "Texture Feature Extractor Based on 2D Local Fourier Transform", Proc. KIPS Spring Conf., 2009.
  17. T. Ojala, T. Maenpa, M. Pietikainen, J. Viertola, J. Kyllonen, and S. Huovinen, "Outex-A New framework for Empirical Evaluation of Texture Analysis Algorithms," Proc. ICPR, vol. 1, pp. 701-706, 2002.
  18. J. S. Weszka, C. R. Dyer, and A. Rosenfeld, "A comparative study of texture measures for terrain classification," IEEE Trans. R.., Man, Cybern.,vol. SMC-6vol. SM69-285, 1976. https://doi.org/10.1109/TSMC.1976.5408777
  19. M. M. Galloway, "Texture Analysis using Gray Level Run Lengths," Computer Graphics and Imag. Processing, vol. 4, pp. 172-179, 1975. https://doi.org/10.1016/S0146-664X(75)80008-6
  20. R. M. Haralick, K. Shanmugan, and I. Dinstein, "Textural Features for Image Classification," IEEE Trans. System, Man, and Cybernetics, vol. SMC-3, no. 6, pp. 610-621, November 1973.
  21. Sorensen L, Shaker SB, de Bruijne M., "Quantitative analysis of pulmonary emphysema using local binary patterns", IEEE Trans. Med Imaging. 29(2), pp. 559-69, 2010. https://doi.org/10.1109/TMI.2009.2038575
  22. Shao-Hu Peng, Khairul-Muzzammil Saipullah, Deok-Hwan Kim, "Quantitative Image Analysis of Chest CT Using Gray Level Local Binary Pattern", International Conference on Convergence Content, pp. 129, 2009.